Deep Coupled Metric Learning for Cross-Modal Matching

In this paper, we propose a new deep coupled metric learning (DCML) method for cross-modal matching, which aims to match samples captured from two different modalities (e.g., texts versus images, visible versus near infrared images). Unlike existing cross-modal matching methods which learn a linear common space to reduce the modality gap, our DCML designs two feedforward neural networks which learn two sets of hierarchical nonlinear transformations (one set for each modality) to nonlinearly map samples from different modalities into a shared latent feature subspace, under which the intraclass variation is minimized and the interclass variation is maximized, and the difference of each data pair captured from two modalities of the same class is minimized, respectively. Experimental results on four different cross-modal matching datasets validate the efficacy of the proposed approach.